Ronghui Xu
Xiaohui Yu
Skip Abstract Section
Abstract
The prevalence of location-based services has generated a deluge of check-ins, enabling the task of human mobility understanding. Among the various types of information associated with the check-in venues, categories (e.g., Bar and Museum) are vital to the task, as they often serve as excellent semantic characterization of the venues. Despite its significance and importance, a large portion of venues in the check-in services do not have even a single category label, such as up to 30% of venues in the Foursquare system lacking category labels. We, therefore, address the problem of semantic venue annotation, i.e., labeling the venue with a semantic category. Existing methods either fail to fully exploit the contextual information in the check-in sequences, or do not consider the semantic correlations across related categories. As such, we devise a Tree-guided Multi-task Embedding model (TME for short) to learn effective representations of venues and categories for the semantic annotation. TME jointly learns a common feature space by modeling multi-contexts of check-ins and utilizes the predefined category hierarchy to regularize the relatedness among categories. We evaluate TME over the task of semantic venue annotation on two check-in datasets. Experimental results show the superiority of TME over several state-of-the-art baselines.
- [1] . 2018. A collaborative ranking model with multiple location-based similarities for venue suggestion. In Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval. 19–26.Google Scholar
Digital Library
- [2] . 2019. Joint learning of hierarchical word embeddings from a corpus and a taxonomy. In Proceedings of the Automated Knowledge Base Construction.Google Scholar
- [3] . 2008. Consistency of the group lasso and multiple kernel learning. Journal of Machine Learning Research 9, 6 (2008), 1179–1225.Google ScholarDigital Library
- [4] . 1997. Multitask learning. Machine Learning 28, 1 (1997), 41–75.Google ScholarDigital Library
- [5] . 2014. On the semantic annotation of daily places: A machine-learning approach. In Proceedings of the 4th International Workshop on Location and the Web. 3–8.Google ScholarDigital Library
- [6] . 2021. Multi-task learning for simultaneous script identification and keyword spotting in document images. Pattern Recognition 113, C (2021), 107832.Google ScholarCross Ref
- [7] . 2019. Fine-grained product categorization in e-commerce. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management. 2349–2352.Google ScholarDigital Library
- [8] . 2021. Multi-context embedding-based personalized place semantics recognition. Information Processing and Management 58, 1 (2021), 102416.Google ScholarCross Ref
- [9] . 2019. MPE: A mobility pattern embedding model for predicting next locations. World Wide Web 22, 6 (2019), 2901–2920.Google ScholarCross Ref
- [10] . 2020. Modeling spatial trajectories with attribute representation learning. IEEE Transactions on Knowledge and Data Engineering 34, 4 (2020), 1902–1914.Google ScholarCross Ref
- [11] . 2021. Embedding hierarchical structures for venue category representation. ACM Transactions on Information Systems 40, 3 (2021), 1–29.Google ScholarDigital Library
- [12] . 2019. PBEM: A pattern-based embedding model for user location category prediction. In Proceedings of the 12th International Conference on Mobile Computing and Ubiquitous Network. 1–6.Google ScholarCross Ref
- [13] . 2014. What is this place? Inferring place categories through user patterns identification in geo-tagged tweets. In Proceedings of the 6th International Conference on Mobile Computing, Applications, and Services. 10–19.Google ScholarCross Ref
- [14] . 2017. HD-MTL: Hierarchical deep multi-task learning for large-scale visual recognition. IEEE Transactions on Image Processing 26, 4 (2017), 1923–1938.Google ScholarDigital Library
- [15] . 2020. Deep hierarchical classification for category prediction in e-commerce system. In Proceedings of the 3rd Workshop on e-Commerce and NLP. 64–68.Google Scholar
- [16] . 2016. A spatial-temporal topic model for the semantic annotation of POIs in LBSNs. ACM Transactions on Intelligent Systems and Technology 8, 1 (2016), 1–24.Google ScholarDigital Library
- [17] . 1993. Using statistical testing in the evaluation of retrieval experiments. In Proceedings of the 16th International ACM SIGIR Conference on Research and Development in Information Retrieval. 329–338.Google ScholarDigital Library
- [18] . 2013. Placer: Semantic place labels from diary data. In Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing. 163–172.Google ScholarDigital Library
- [19] . 2014. Neural word embedding as implicit matrix factorization. In Proceedings of the 27th International Conference on Neural Information Processing Systems. 2177–2185.Google Scholar
- [20] . 2020. Annotating semantic tags of locations in location-based social networks. GeoInformatica 24, 1 (2020), 133–152.Google ScholarDigital Library
- [21] . 2019. Improving person re-identification by multi-task learning. Neurocomputing 347 (2019), 109–118. Google ScholarDigital Library
- [22] . 2012. Dense neighborhoods on affinity graph. International Journal of Computer Vision 98, 1 (2012), 65–82.Google ScholarDigital Library
- [23] . 2018. Semantic structure-based word embedding by incorporating concept convergence and word divergence. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence. 5261–5268.Google ScholarCross Ref
- [24] . 2016. Traffic sign recognition via multi-modal tree-structure embedded multi-task learning. IEEE Transactions on Intelligent Transportation Systems 18, 4 (2016), 960–972.Google ScholarDigital Library
- [25] . 2021. A survey on deep learning for human mobility. ACM Computing Surveys 55, 1 (2021), 1–44.Google ScholarDigital Library
- [26] . 2017. An adaptive semisupervised feature analysis for video semantic recognition. IEEE Transactions on Cybernetics 48, 2 (2017), 648–660.Google ScholarCross Ref
- [27] . 2016. The discovery of personally semantic places based on trajectory data mining. Neurocomputing 173 (2016), 1142–1153. Google ScholarDigital Library
- [28] . 2018. A contextual attention recurrent architecture for context-aware venue recommendation. In Proceedings of the 41st International ACM SIGIR Conference on Research and Development in Information Retrieval. 555–564.Google ScholarDigital Library
- [29] . 2017. A deep multi-modal fusion approach for semantic place prediction in social media. In Proceedings of the Workshop on Multimodal Understanding of Social, Affective, and Subjective Attributes. 31–37.Google ScholarDigital Library
- [30] . 2013. Distributed representations of words and phrases and their compositionality. In Proceedings of the 27th Annual Conference on Neural Information Processing Systems. 3111–3119.Google ScholarDigital Library
- [31] . 2020. Heterogeneous graph-based joint representation learning for users and POIs in location-based social network. Information Processing and Management 57, 2 (2020), 102151.Google ScholarDigital Library
- [32] . 2019. Category-aware location embedding for point-of-interest recommendation. In Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval. 173–176.Google ScholarDigital Library
- [33] . 2020. E-commerce product categorization via machine translation. ACM Transactions on Management Information Systems 11, 3 (2020), 1–14.Google ScholarDigital Library
- [34] . 2017. LCE: A location category embedding model for predicting the category labels of POIs. In Proceedings of the 2017 International Conference on Neural Information Processing. 710–720.Google ScholarDigital Library
- [35] . 2017. Cost-sensitive semi-supervised personalized semantic place label recognition using multi-context data. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 1, 3 (2017), 1–14.Google ScholarDigital Library
- [36] . 2020. Semantics-preserving graph propagation for zero-shot object detection. IEEE Transactions on Image Processing 29 (2020), 8163–8176. Google ScholarDigital Library
- [37] . 2017. A neural network approach to jointly modeling social networks and mobile trajectories. ACM Transactions on Information Systems 35, 4 (2017), 1–28.Google ScholarDigital Library
- [38] . 2019. Revisiting user mobility and social relationships in LBSNs: A hypergraph embedding approach. In Proceedings of the Web Conference. 2147–2157.Google ScholarDigital Library
- [39] . 2016. Participatory cultural mapping based on collective behavior data in location-based social networks. ACM Transactions on Intelligent Systems and Technology 7, 3 (2016), 30.Google ScholarDigital Library
- [40] . 2018. Unsupervised learning of parsimonious general-purpose embeddings for user and location modeling. ACM Transactions on Information Systems 36, 3 (2018), 32.Google ScholarDigital Library
- [41] . 2011. On the semantic annotation of places in location-based social networks. In Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 520–528.Google ScholarDigital Library
- [42] . 2019. Time-aware metric embedding with asymmetric projection for successive POI recommendation. World Wide Web 22, 5 (2019), 2209–2224.Google ScholarDigital Library
- [43] . 2020. A category-aware deep model for successive POI recommendation on sparse check-in data. In Proceedings of the Web Conference. 1264–1274.Google ScholarDigital Library
- [44] . 2006. Model selection and estimation in regression with grouped variables. Journal of the Royal Statistical Society: Series B (Statistical Methodology) 68, 1 (2006), 49–67.Google ScholarCross Ref
- [45] . 2017. Large-scale point-of-interest category prediction using natural language processing models. In Proceedings of the 2017 IEEE International Conference on Big Data. 1027–1032.Google ScholarCross Ref
- [46] . 2016. Shorter-is-better: Venue category estimation from micro-video. In Proceedings of the 24th ACM International Conference on Multimedia. 1415–1424.Google ScholarDigital Library
- [47] . 2017. Geo-teaser: Geo-temporal Sequential embedding rank for point-of-interest recommendation. In Proceedings of the 26th International Conference on World Wide Web Companion. 153–162.Google ScholarDigital Library
- [48] . 2018. Joint representation learning for location-based social networks with multi-grained sequential contexts. ACM Transactions on Knowledge Discovery from Data 12, 2 (2018), 1–21.Google ScholarDigital Library
- [49] . 2020. Hierarchy-aware global model for hierarchical text classification. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 1106–1117.Google ScholarCross Ref
- [50] . 2016. A general multi-context embedding model for mining human trajectory data. IEEE Transactions on Knowledge and Data Engineering 28, 8 (2016), 1945–1958.Google ScholarDigital Library
- [51] . 2013. Feature engineering for semantic place prediction. Pervasive and Mobile Computing 9, 6 (2013), 772–783.Google ScholarDigital Library
Index Terms
- TME: Tree-guided Multi-task Embedding Learning towards Semantic Venue Annotation
Recommendations
Embedding Hierarchical Structures for Venue Category Representation
Venue categories used in location-based social networks often exhibit a hierarchical structure, together with the category sequences derived from users’ check-ins. The two data modalities provide a wealth of information for us to capture the semantic ...
Enabling the interpretability of pretrained venue representations using semantic categories
AbstractThe growing popularity of location-based social networks gives rise to a tremendous amount of social check-ins data, which are broadly used in previous studies to produce dense venue representations for various trajectory mining tasks. ...
Highlights- Propose an embedding model to yield representations of venues and categories.
- ...
LCE: A Location Category Embedding Model for Predicting the Category Labels of POIs
Neural Information ProcessingAbstractThe proliferation of location-based social networks, makes it possible to record human mobility using an array of points-of-interest (POIs). Exploring the semantic meanings of POIs can be of great importance to many urban computing applications, ...
Comments